Pixel-level Manipulation Detection on COVER
83.2F1 ScoreMVSS-Net++
Evaluation results
| Method | Links | |
|---|---|---|
| MVSS-Net++Threshold Strategy=Optimal threshold per model & testset, Training Data=CASIAv22021.12 | 83.2 | |
| MVSS-NetThresholding strategy=Optimal threshold per model & testset, Training dataset=CASIAv22021.04 | 82.4 | |
| MVSS-NetThreshold Strategy=Optimal threshold per model & testset, Training Data=CASIAv22021.12 | 82.4 | |
| ManTra-NetThresholding strategy=Optimal threshold per model & testset, Training dataset=Other (Not CASIAv2)2021.04 | 77.2 | |
| ManTra-NetThreshold Strategy=Optimal threshold per model & testset, Training Data=Private2021.12 | 77.2 | |
| SPANThreshold Strategy=Optimal threshold per model & testset, Training Data=Private2021.12 | 71.8 | |
| FCNThresholding strategy=Optimal threshold per model & testset, Training dataset=CASIAv22021.04 | 57.3 | |
| FCNThreshold Strategy=Optimal threshold per model & testset, Training Data=CASIAv22021.12 | 57.3 | |
| GSR-NetThresholding strategy=Optimal threshold per model & testset, Training dataset=CASIAv22021.04 | 48.9 | |
| GSR-NetThreshold Strategy=Optimal threshold per model & testset, Training Data=CASIAv22021.12 | 48.9 | |
| CAT-NetThreshold Strategy=Optimal threshold per model & testset, Training Data=Private2021.12 | 48.5 | |
| MVSS-Net++Threshold Strategy=Fixed threshold (0.5), Training Data=CASIAv22021.12 | 48.2 | |
| CR-CNNThresholding strategy=Optimal threshold per model & testset, Training dataset=CASIAv22021.04 | 47 | |
| CR-CNNThreshold Strategy=Optimal threshold per model & testset, Training Data=CASIAv22021.12 | 47 | |
| MVSS-NetThresholding strategy=Fixed threshold (0.5), Training dataset=CASIAv22021.04 | 45.3 | |
| MVSS-NetThreshold Strategy=Fixed threshold (0.5), Training Data=CASIAv22021.12 | 45.3 | |
| RGB-NThresholding strategy=Optimal threshold per model & testset, Training dataset=CASIAv22021.04 | 37.9 | |
| RGB-NThreshold Strategy=Optimal threshold per model & testset, Training Data=CASIAv22021.12 | 37.9 | |
| CR-CNNThresholding strategy=Fixed threshold (0.5), Training dataset=CASIAv22021.04 | 29.1 | |
| CR-CNNThreshold Strategy=Fixed threshold (0.5), Training Data=CASIAv22021.12 | 29.1 | |
| ManTra-NetThresholding strategy=Fixed threshold (0.5), Training dataset=Other (Not CASIAv2)2021.04 | 28.6 | |
| ManTra-NetThreshold Strategy=Fixed threshold (0.5), Training Data=Private2021.12 | 28.6 | |
| GSR-NetThresholding strategy=Fixed threshold (0.5), Training dataset=CASIAv22021.04 | 28.5 | |
| GSR-NetThreshold Strategy=Fixed threshold (0.5), Training Data=CASIAv22021.12 | 28.5 | |
| H-LSTMThreshold Strategy=Optimal threshold per model & testset, Training Data=Published but no longer publicly accessible data2021.12 | 21.3 | |
| HP-FCNThresholding strategy=Optimal threshold per model & testset, Training dataset=Other (Not CASIAv2)2021.04 | 19.9 | |
| FCNThresholding strategy=Fixed threshold (0.5), Training dataset=CASIAv22021.04 | 19.9 | |
| HP-FCNThreshold Strategy=Optimal threshold per model & testset, Training Data=Private2021.12 | 19.9 | |
| FCNThreshold Strategy=Fixed threshold (0.5), Training Data=CASIAv22021.12 | 19.9 | |
| SPANThreshold Strategy=Fixed threshold (0.5), Training Data=Private2021.12 | 17.2 | |
| H-LSTMThreshold Strategy=Fixed threshold (0.5), Training Data=Published but no longer publicly accessible data2021.12 | 16.3 | |
| CAT-NetThreshold Strategy=Fixed threshold (0.5), Training Data=Private2021.12 | 12.9 | |
| HP-FCNThresholding strategy=Fixed threshold (0.5), Training dataset=Other (Not CASIAv2)2021.04 | 0.3 | |
| HP-FCNThreshold Strategy=Fixed threshold (0.5), Training Data=Private2021.12 | 0.3 |